MAINLOBE INTERFERENCE SUPPRESSION METHOD BASED ON BLIND SOURCE SEPARATION WITH SUPPORT VECTOR MACHINE

The mainlobe interference causes seriously affects on the performance of radar system. Besides, the traditional adaptive beamforming method would severely deteriorate when the desired signal is contained in the training snapshots. In order to solve the problem, a mainlobe interference suppression method based on blind source separation with support vector machine is proposed in this paper. In the proposed method, the DOA estimation is used on the array received data to determine the number of separated signal channels. Then the blind source separation algorithm is used to separate the received signals to obtain independent target and interference signal waveforms. Finally, high-order features are extracted in the transform domain, and support vector machine (SVM) is used for target and interference identification for determining the target signal channel and completing interference suppression. The actual measured data processing results show that this method can effectively resist mainlobe suppression and deception interference.